SentenceTransformer based on intfloat/multilingual-e5-large-instruct

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-large-instruct. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: intfloat/multilingual-e5-large-instruct
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'})
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("meandyou200175/E5_v3_instruct_topic")
# Run inference
sentences = [
    'task: sentence similarity | query: tập hợp 500 tờ giấy hay 20 thếp giấy, làm thành đơn vị để tính số lượng giấy',
    'in hết hai ram giấy',
    'Tổ chức toàn cầu',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  0.8042, -0.0971],
#         [ 0.8042,  1.0000, -0.1152],
#         [-0.0971, -0.1152,  1.0000]])

Evaluation

Metrics

Information Retrieval

Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.162
cosine_accuracy@2	0.2119
cosine_accuracy@5	0.2903
cosine_accuracy@10	0.3639
cosine_accuracy@100	0.754
cosine_precision@1	0.162
cosine_precision@2	0.106
cosine_precision@5	0.0581
cosine_precision@10	0.0364
cosine_precision@100	0.0075
cosine_recall@1	0.162
cosine_recall@2	0.2119
cosine_recall@5	0.2903
cosine_recall@10	0.3639
cosine_recall@100	0.754
cosine_ndcg@10	0.2521
cosine_mrr@1	0.162
cosine_mrr@2	0.187
cosine_mrr@5	0.2079
cosine_mrr@10	0.2177
cosine_mrr@100	0.2312
cosine_map@100	0.2312

Training Details

Training Dataset

Unnamed Dataset

Size: 97,975 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 14 tokens
mean: 134.34 tokens
max: 290 tokens

min: 3 tokens
mean: 8.03 tokens
max: 41 tokens

	anchor	positive
type	string	string
details	min: 14 tokens mean: 134.34 tokens max: 290 tokens	min: 3 tokens mean: 8.03 tokens max: 41 tokens

Samples:

anchor	positive
`task: sentence similarity \| query: luống`	`trồng mấy liếp rau`
`task: sentence similarity \| query: không còn có quan hệ tình cảm và tình dục, do bất hoà`	`vợ chồng sống li thân`
`task: sentence similarity \| query: đánh bật khỏi một vị trí, một địa vị nào đó để chiếm lấy`	`Nhật hất cẳng Pháp ở chiến trường Đông Dương`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Evaluation Dataset

Unnamed Dataset

Size: 10,887 evaluation samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 13 tokens
mean: 126.94 tokens
max: 281 tokens

min: 3 tokens
mean: 7.72 tokens
max: 35 tokens

	anchor	positive
type	string	string
details	min: 13 tokens mean: 126.94 tokens max: 281 tokens	min: 3 tokens mean: 7.72 tokens max: 35 tokens

Samples:

anchor	positive
`task: sentence similarity \| query: dải phù sa ở dọc sông hay cửa sông`	`doi cát`
task: classification \| query: Theo hãng phân tích JP Morgan, Apple khả năng kỳ vọng Phố Wall quý 2, bất chấp vấn đề chuỗi cung ứng biến động kinh tế vĩ mô. Cụ thể, ghi gửi đầu tư, phân tích Samik Chatterjee JP Morgan hay, "không lo lắng Phố Wall" báo cáo doanh thu Apple – dự kiến công bố 28/7. Mặc rủi ro trung hạn, hy vọng doanh thu doanh iPhone mẽ. iPhone 13 Series "đắt hàng". Nhà phân tích định, chuỗi cung ứng cải thiện yếu kém nhu cầu dự đoán, Apple doanh thu 4 - 8 tỷ USD 3 (tháng 4 – 6). Phố Wall dự kiến, "Nhà Táo" báo cáo doanh thu 82 tỷ USD quý 2, tương đương kỳ vọng 82,1 tỷ USD Chatterjee. Thêm nữa, phân tích hay, phân khúc sản phẩm Mac thể ảnh hưởng cung cấp. Mặt khác, quý nhất, Chatterjee doanh thu dự kiến khiêm tốn. Ông tốc độ trưởng Mac iPad khả năng chi tiêu tiêu xuống. iPhone 11 giá Việt Nam.	`Sức khỏe - Đời sống`
`task: classification \| query: Khó thống nhất việc hiệp thương giá bán than`
Cuộc họp do Bộ Tài chính chủ trì với sự tham gia của Bộ Công nghiệp, Tổng công ty Than Việt Nam (TVN) cuối tuần qua đã đi đến kết luận TVN sẽ tiến hành hiệp thương về giá với các đơn vị tiêu thụ lớn trong vòng 15 ngày tới.
Trong trường hợp hai bên mua bán không hiệp thương được thì cơ quan hữu trách sẽ có những biện pháp giải quyết. Trước đó, các cơ quan hữu trách đã yêu cầu TVN trong thời gian hiệp thương về giá vẫn phải đảm bảo cung cấp đủ than cho các hộ tiêu thụ lớn với mức giá tạm tính theo giá của quý IV năm nay.
Bình luận về việc hiệp thương giá giữa TVN và các hộ tiêu thụ lớn, các chuyên gia cho rằng khó có thể đi đến kết quả thống nhất bởi quyền lợi mỗi bên rất khác nhau.	`Kinh doanh`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 4
per_device_eval_batch_size: 4
learning_rate: 2e-05
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 4
per_device_eval_batch_size: 4
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 3
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss	cosine_ndcg@10
0.0041	100	0.8086	-	-
0.0082	200	0.634	-	-
0.0122	300	0.384	-	-
0.0163	400	0.2215	-	-
0.0204	500	0.2331	-	-
0.0245	600	0.1441	-	-
0.0286	700	0.1713	-	-
0.0327	800	0.1093	-	-
0.0367	900	0.1514	-	-
0.0408	1000	0.137	-	-
0.0449	1100	0.1053	-	-
0.0490	1200	0.1869	-	-
0.0531	1300	0.1046	-	-
0.0572	1400	0.1653	-	-
0.0612	1500	0.1365	-	-
0.0653	1600	0.176	-	-
0.0694	1700	0.1587	-	-
0.0735	1800	0.107	-	-
0.0776	1900	0.1624	-	-
0.0817	2000	0.1153	-	-
0.0857	2100	0.0807	-	-
0.0898	2200	0.1341	-	-
0.0939	2300	0.1293	-	-
0.0980	2400	0.1682	-	-
0.1021	2500	0.1393	-	-
0.1061	2600	0.0938	-	-
0.1102	2700	0.0809	-	-
0.1143	2800	0.1414	-	-
0.1184	2900	0.0914	-	-
0.1225	3000	0.1292	-	-
0.1266	3100	0.1326	-	-
0.1306	3200	0.1346	-	-
0.1347	3300	0.1204	-	-
0.1388	3400	0.1715	-	-
0.1429	3500	0.0749	-	-
0.1470	3600	0.1159	-	-
0.1511	3700	0.1199	-	-
0.1551	3800	0.0963	-	-
0.1592	3900	0.0933	-	-
0.1633	4000	0.0748	-	-
0.1674	4100	0.1901	-	-
0.1715	4200	0.1454	-	-
0.1756	4300	0.083	-	-
0.1796	4400	0.1796	-	-
0.1837	4500	0.0992	-	-
0.1878	4600	0.1476	-	-
0.1919	4700	0.1276	-	-
0.1960	4800	0.1516	-	-
0.2000	4900	0.1725	-	-
0.2041	5000	0.1894	-	-
0.2082	5100	0.055	-	-
0.2123	5200	0.1373	-	-
0.2164	5300	0.0768	-	-
0.2205	5400	0.0781	-	-
0.2245	5500	0.1315	-	-
0.2286	5600	0.1501	-	-
0.2327	5700	0.1596	-	-
0.2368	5800	0.1418	-	-
0.2409	5900	0.2087	-	-
0.2450	6000	0.1066	-	-
0.2490	6100	0.1905	-	-
0.2531	6200	0.1913	-	-
0.2572	6300	0.1176	-	-
0.2613	6400	0.0991	-	-
0.2654	6500	0.0753	-	-
0.2695	6600	0.1405	-	-
0.2735	6700	0.2123	-	-
0.2776	6800	0.1311	-	-
0.2817	6900	0.1173	-	-
0.2858	7000	0.1801	-	-
0.2899	7100	0.2224	-	-
0.2939	7200	0.1592	-	-
0.2980	7300	0.1467	-	-
0.3021	7400	0.1743	-	-
0.3062	7500	0.1822	-	-
0.3103	7600	0.2163	-	-
0.3144	7700	0.242	-	-
0.3184	7800	0.1227	-	-
0.3225	7900	0.1577	-	-
0.3266	8000	0.1528	-	-
0.3307	8100	0.1352	-	-
0.3348	8200	0.1447	-	-
0.3389	8300	0.1673	-	-
0.3429	8400	0.13	-	-
0.3470	8500	0.137	-	-
0.3511	8600	0.2145	-	-
0.3552	8700	0.1964	-	-
0.3593	8800	0.1278	-	-
0.3634	8900	0.1467	-	-
0.3674	9000	0.2462	-	-
0.3715	9100	0.1452	-	-
0.3756	9200	0.1748	-	-
0.3797	9300	0.2234	-	-
0.3838	9400	0.0991	-	-
0.3879	9500	0.091	-	-
0.3919	9600	0.067	-	-
0.3960	9700	0.2475	-	-
0.4001	9800	0.2083	-	-
0.4042	9900	0.1617	-	-
0.4083	10000	0.2144	0.1217	0.1954
0.4123	10100	0.1944	-	-
0.4164	10200	0.2178	-	-
0.4205	10300	0.137	-	-
0.4246	10400	0.1847	-	-
0.4287	10500	0.1123	-	-
0.4328	10600	0.1133	-	-
0.4368	10700	0.1968	-	-
0.4409	10800	0.1281	-	-
0.4450	10900	0.118	-	-
0.4491	11000	0.1245	-	-
0.4532	11100	0.145	-	-
0.4573	11200	0.2029	-	-
0.4613	11300	0.0952	-	-
0.4654	11400	0.0998	-	-
0.4695	11500	0.1336	-	-
0.4736	11600	0.0828	-	-
0.4777	11700	0.1727	-	-
0.4818	11800	0.1549	-	-
0.4858	11900	0.1687	-	-
0.4899	12000	0.1231	-	-
0.4940	12100	0.1485	-	-
0.4981	12200	0.1387	-	-
0.5022	12300	0.1272	-	-
0.5062	12400	0.1073	-	-
0.5103	12500	0.1157	-	-
0.5144	12600	0.1419	-	-
0.5185	12700	0.1449	-	-
0.5226	12800	0.1537	-	-
0.5267	12900	0.1398	-	-
0.5307	13000	0.2289	-	-
0.5348	13100	0.1949	-	-
0.5389	13200	0.1291	-	-
0.5430	13300	0.1461	-	-
0.5471	13400	0.1095	-	-
0.5512	13500	0.1744	-	-
0.5552	13600	0.102	-	-
0.5593	13700	0.1321	-	-
0.5634	13800	0.216	-	-
0.5675	13900	0.16	-	-
0.5716	14000	0.1249	-	-
0.5757	14100	0.1204	-	-
0.5797	14200	0.2567	-	-
0.5838	14300	0.1651	-	-
0.5879	14400	0.1719	-	-
0.5920	14500	0.0986	-	-
0.5961	14600	0.1748	-	-
0.6001	14700	0.1206	-	-
0.6042	14800	0.055	-	-
0.6083	14900	0.0976	-	-
0.6124	15000	0.1733	-	-
0.6165	15100	0.0655	-	-
0.6206	15200	0.0831	-	-
0.6246	15300	0.1799	-	-
0.6287	15400	0.1579	-	-
0.6328	15500	0.1342	-	-
0.6369	15600	0.1398	-	-
0.6410	15700	0.1391	-	-
0.6451	15800	0.0943	-	-
0.6491	15900	0.1103	-	-
0.6532	16000	0.2546	-	-
0.6573	16100	0.1479	-	-
0.6614	16200	0.2913	-	-
0.6655	16300	0.1974	-	-
0.6696	16400	0.1827	-	-
0.6736	16500	0.167	-	-
0.6777	16600	0.1555	-	-
0.6818	16700	0.163	-	-
0.6859	16800	0.1291	-	-
0.6900	16900	0.1903	-	-
0.6940	17000	0.163	-	-
0.6981	17100	0.15	-	-
0.7022	17200	0.1153	-	-
0.7063	17300	0.1333	-	-
0.7104	17400	0.1228	-	-
0.7145	17500	0.1387	-	-
0.7185	17600	0.1689	-	-
0.7226	17700	0.1073	-	-
0.7267	17800	0.1984	-	-
0.7308	17900	0.08	-	-
0.7349	18000	0.2067	-	-
0.7390	18100	0.201	-	-
0.7430	18200	0.1861	-	-
0.7471	18300	0.1046	-	-
0.7512	18400	0.1834	-	-
0.7553	18500	0.1149	-	-
0.7594	18600	0.1612	-	-
0.7635	18700	0.1294	-	-
0.7675	18800	0.1522	-	-
0.7716	18900	0.1033	-	-
0.7757	19000	0.1242	-	-
0.7798	19100	0.1068	-	-
0.7839	19200	0.1133	-	-
0.7879	19300	0.0551	-	-
0.7920	19400	0.113	-	-
0.7961	19500	0.0966	-	-
0.8002	19600	0.1611	-	-
0.8043	19700	0.1038	-	-
0.8084	19800	0.1313	-	-
0.8124	19900	0.0831	-	-
0.8165	20000	0.0938	0.1143	0.1925
0.8206	20100	0.0894	-	-
0.8247	20200	0.0834	-	-
0.8288	20300	0.0886	-	-
0.8329	20400	0.0774	-	-
0.8369	20500	0.1678	-	-
0.8410	20600	0.094	-	-
0.8451	20700	0.1003	-	-
0.8492	20800	0.1609	-	-
0.8533	20900	0.1413	-	-
0.8574	21000	0.1334	-	-
0.8614	21100	0.0822	-	-
0.8655	21200	0.15	-	-
0.8696	21300	0.1048	-	-
0.8737	21400	0.2185	-	-
0.8778	21500	0.1265	-	-
0.8818	21600	0.1064	-	-
0.8859	21700	0.1448	-	-
0.8900	21800	0.1769	-	-
0.8941	21900	0.0884	-	-
0.8982	22000	0.133	-	-
0.9023	22100	0.1228	-	-
0.9063	22200	0.0732	-	-
0.9104	22300	0.154	-	-
0.9145	22400	0.1479	-	-
0.9186	22500	0.1305	-	-
0.9227	22600	0.1797	-	-
0.9268	22700	0.1242	-	-
0.9308	22800	0.1039	-	-
0.9349	22900	0.0928	-	-
0.9390	23000	0.127	-	-
0.9431	23100	0.1123	-	-
0.9472	23200	0.1412	-	-
0.9513	23300	0.0831	-	-
0.9553	23400	0.113	-	-
0.9594	23500	0.0691	-	-
0.9635	23600	0.1093	-	-
0.9676	23700	0.182	-	-
0.9717	23800	0.1324	-	-
0.9757	23900	0.0964	-	-
0.9798	24000	0.0522	-	-
0.9839	24100	0.1533	-	-
0.9880	24200	0.1123	-	-
0.9921	24300	0.2087	-	-
0.9962	24400	0.1461	-	-
1.0002	24500	0.1227	-	-
1.0043	24600	0.0947	-	-
1.0084	24700	0.1119	-	-
1.0125	24800	0.161	-	-
1.0166	24900	0.1634	-	-
1.0207	25000	0.1679	-	-
1.0247	25100	0.0946	-	-
1.0288	25200	0.1324	-	-
1.0329	25300	0.0625	-	-
1.0370	25400	0.0604	-	-
1.0411	25500	0.0513	-	-
1.0452	25600	0.0878	-	-
1.0492	25700	0.0453	-	-
1.0533	25800	0.1287	-	-
1.0574	25900	0.0698	-	-
1.0615	26000	0.0465	-	-
1.0656	26100	0.0647	-	-
1.0696	26200	0.059	-	-
1.0737	26300	0.0903	-	-
1.0778	26400	0.1236	-	-
1.0819	26500	0.1042	-	-
1.0860	26600	0.1404	-	-
1.0901	26700	0.101	-	-
1.0941	26800	0.142	-	-
1.0982	26900	0.146	-	-
1.1023	27000	0.1452	-	-
1.1064	27100	0.0434	-	-
1.1105	27200	0.0748	-	-
1.1146	27300	0.1617	-	-
1.1186	27400	0.0877	-	-
1.1227	27500	0.108	-	-
1.1268	27600	0.1063	-	-
1.1309	27700	0.1022	-	-
1.1350	27800	0.0592	-	-
1.1391	27900	0.1477	-	-
1.1431	28000	0.0677	-	-
1.1472	28100	0.0661	-	-
1.1513	28200	0.116	-	-
1.1554	28300	0.0458	-	-
1.1595	28400	0.0689	-	-
1.1636	28500	0.1099	-	-
1.1676	28600	0.0423	-	-
1.1717	28700	0.0807	-	-
1.1758	28800	0.0352	-	-
1.1799	28900	0.0321	-	-
1.1840	29000	0.0796	-	-
1.1880	29100	0.0684	-	-
1.1921	29200	0.1478	-	-
1.1962	29300	0.057	-	-
1.2003	29400	0.1524	-	-
1.2044	29500	0.0733	-	-
1.2085	29600	0.0301	-	-
1.2125	29700	0.1199	-	-
1.2166	29800	0.0823	-	-
1.2207	29900	0.0766	-	-
1.2248	30000	0.1003	0.1013	0.2033
1.2289	30100	0.1279	-	-
1.2330	30200	0.0519	-	-
1.2370	30300	0.1175	-	-
1.2411	30400	0.0471	-	-
1.2452	30500	0.1043	-	-
1.2493	30600	0.0945	-	-
1.2534	30700	0.1124	-	-
1.2575	30800	0.0261	-	-
1.2615	30900	0.0767	-	-
1.2656	31000	0.1133	-	-
1.2697	31100	0.1257	-	-
1.2738	31200	0.1037	-	-
1.2779	31300	0.1029	-	-
1.2819	31400	0.1238	-	-
1.2860	31500	0.1058	-	-
1.2901	31600	0.03	-	-
1.2942	31700	0.0735	-	-
1.2983	31800	0.1059	-	-
1.3024	31900	0.0779	-	-
1.3064	32000	0.118	-	-
1.3105	32100	0.0754	-	-
1.3146	32200	0.0904	-	-
1.3187	32300	0.0651	-	-
1.3228	32400	0.0969	-	-
1.3269	32500	0.096	-	-
1.3309	32600	0.1205	-	-
1.3350	32700	0.1657	-	-
1.3391	32800	0.0552	-	-
1.3432	32900	0.0654	-	-
1.3473	33000	0.0764	-	-
1.3514	33100	0.0764	-	-
1.3554	33200	0.0803	-	-
1.3595	33300	0.0563	-	-
1.3636	33400	0.0579	-	-
1.3677	33500	0.0959	-	-
1.3718	33600	0.1009	-	-
1.3758	33700	0.0732	-	-
1.3799	33800	0.0368	-	-
1.3840	33900	0.0936	-	-
1.3881	34000	0.0998	-	-
1.3922	34100	0.0523	-	-
1.3963	34200	0.109	-	-
1.4003	34300	0.0958	-	-
1.4044	34400	0.112	-	-
1.4085	34500	0.0849	-	-
1.4126	34600	0.0582	-	-
1.4167	34700	0.1075	-	-
1.4208	34800	0.1039	-	-
1.4248	34900	0.0935	-	-
1.4289	35000	0.0717	-	-
1.4330	35100	0.0539	-	-
1.4371	35200	0.1003	-	-
1.4412	35300	0.0525	-	-
1.4453	35400	0.0764	-	-
1.4493	35500	0.1041	-	-
1.4534	35600	0.0788	-	-
1.4575	35700	0.0266	-	-
1.4616	35800	0.069	-	-
1.4657	35900	0.0454	-	-
1.4697	36000	0.1107	-	-
1.4738	36100	0.0629	-	-
1.4779	36200	0.0971	-	-
1.4820	36300	0.1667	-	-
1.4861	36400	0.1184	-	-
1.4902	36500	0.0755	-	-
1.4942	36600	0.0911	-	-
1.4983	36700	0.0576	-	-
1.5024	36800	0.051	-	-
1.5065	36900	0.1865	-	-
1.5106	37000	0.0528	-	-
1.5147	37100	0.0703	-	-
1.5187	37200	0.0438	-	-
1.5228	37300	0.1311	-	-
1.5269	37400	0.0603	-	-
1.5310	37500	0.0748	-	-
1.5351	37600	0.0573	-	-
1.5392	37700	0.1453	-	-
1.5432	37800	0.0877	-	-
1.5473	37900	0.0878	-	-
1.5514	38000	0.0782	-	-
1.5555	38100	0.1503	-	-
1.5596	38200	0.0745	-	-
1.5636	38300	0.0651	-	-
1.5677	38400	0.0509	-	-
1.5718	38500	0.0694	-	-
1.5759	38600	0.0458	-	-
1.5800	38700	0.0701	-	-
1.5841	38800	0.0629	-	-
1.5881	38900	0.0733	-	-
1.5922	39000	0.3135	-	-
1.5963	39100	0.7966	-	-
1.6004	39200	0.0332	-	-
1.6045	39300	0.0804	-	-
1.6086	39400	0.0909	-	-
1.6126	39500	0.0691	-	-
1.6167	39600	0.0931	-	-
1.6208	39700	0.1133	-	-
1.6249	39800	0.088	-	-
1.6290	39900	0.1219	-	-
1.6331	40000	0.0602	0.0841	0.2187
1.6371	40100	0.0958	-	-
1.6412	40200	0.0781	-	-
1.6453	40300	0.1139	-	-
1.6494	40400	0.0751	-	-
1.6535	40500	0.0513	-	-
1.6575	40600	0.1193	-	-
1.6616	40700	0.0958	-	-
1.6657	40800	0.0691	-	-
1.6698	40900	0.0876	-	-
1.6739	41000	0.0605	-	-
1.6780	41100	0.0825	-	-
1.6820	41200	0.0785	-	-
1.6861	41300	0.0639	-	-
1.6902	41400	0.0437	-	-
1.6943	41500	0.072	-	-
1.6984	41600	0.0425	-	-
1.7025	41700	0.1002	-	-
1.7065	41800	0.134	-	-
1.7106	41900	0.107	-	-
1.7147	42000	0.1095	-	-
1.7188	42100	0.0805	-	-
1.7229	42200	0.0618	-	-
1.7270	42300	0.1396	-	-
1.7310	42400	0.0938	-	-
1.7351	42500	0.0678	-	-
1.7392	42600	0.0515	-	-
1.7433	42700	0.0379	-	-
1.7474	42800	0.0637	-	-
1.7514	42900	0.0535	-	-
1.7555	43000	0.0744	-	-
1.7596	43100	0.1076	-	-
1.7637	43200	0.0774	-	-
1.7678	43300	0.0664	-	-
1.7719	43400	0.0286	-	-
1.7759	43500	0.1307	-	-
1.7800	43600	0.0498	-	-
1.7841	43700	0.1007	-	-
1.7882	43800	0.0849	-	-
1.7923	43900	0.1118	-	-
1.7964	44000	0.0524	-	-
1.8004	44100	0.0892	-	-
1.8045	44200	0.0425	-	-
1.8086	44300	0.0873	-	-
1.8127	44400	0.0677	-	-
1.8168	44500	0.0688	-	-
1.8209	44600	0.0494	-	-
1.8249	44700	0.0937	-	-
1.8290	44800	0.0443	-	-
1.8331	44900	0.0577	-	-
1.8372	45000	0.1029	-	-
1.8413	45100	0.0586	-	-
1.8453	45200	0.0704	-	-
1.8494	45300	0.103	-	-
1.8535	45400	0.0485	-	-
1.8576	45500	0.0869	-	-
1.8617	45600	0.1174	-	-
1.8658	45700	0.0326	-	-
1.8698	45800	0.0862	-	-
1.8739	45900	0.062	-	-
1.8780	46000	0.0503	-	-
1.8821	46100	0.0645	-	-
1.8862	46200	0.0633	-	-
1.8903	46300	0.077	-	-
1.8943	46400	0.065	-	-
1.8984	46500	0.0633	-	-
1.9025	46600	0.0575	-	-
1.9066	46700	0.0744	-	-
1.9107	46800	0.0685	-	-
1.9148	46900	0.1058	-	-
1.9188	47000	0.0542	-	-
1.9229	47100	0.0842	-	-
1.9270	47200	0.0719	-	-
1.9311	47300	0.0563	-	-
1.9352	47400	0.0755	-	-
1.9393	47500	0.0571	-	-
1.9433	47600	0.0985	-	-
1.9474	47700	0.0566	-	-
1.9515	47800	0.0428	-	-
1.9556	47900	0.0422	-	-
1.9597	48000	0.0774	-	-
1.9637	48100	0.0489	-	-
1.9678	48200	0.0591	-	-
1.9719	48300	0.0218	-	-
1.9760	48400	0.0584	-	-
1.9801	48500	0.0273	-	-
1.9842	48600	0.0539	-	-
1.9882	48700	0.1092	-	-
1.9923	48800	0.0737	-	-
1.9964	48900	0.0788	-	-
2.0005	49000	0.0654	-	-
2.0046	49100	0.0528	-	-
2.0087	49200	0.0735	-	-
2.0127	49300	0.0535	-	-
2.0168	49400	0.0327	-	-
2.0209	49500	0.0597	-	-
2.0250	49600	0.0357	-	-
2.0291	49700	0.0417	-	-
2.0332	49800	0.0243	-	-
2.0372	49900	0.0774	-	-
2.0413	50000	0.0651	0.0693	0.2269
2.0454	50100	0.0481	-	-
2.0495	50200	0.0658	-	-
2.0536	50300	0.0822	-	-
2.0576	50400	0.0606	-	-
2.0617	50500	0.0542	-	-
2.0658	50600	0.0261	-	-
2.0699	50700	0.0994	-	-
2.0740	50800	0.0617	-	-
2.0781	50900	0.0466	-	-
2.0821	51000	0.075	-	-
2.0862	51100	0.0655	-	-
2.0903	51200	0.0544	-	-
2.0944	51300	0.025	-	-
2.0985	51400	0.0426	-	-
2.1026	51500	0.0448	-	-
2.1066	51600	0.0395	-	-
2.1107	51700	0.0689	-	-
2.1148	51800	0.0556	-	-
2.1189	51900	0.0461	-	-
2.1230	52000	0.0701	-	-
2.1271	52100	0.0583	-	-
2.1311	52200	0.0416	-	-
2.1352	52300	0.0276	-	-
2.1393	52400	0.0216	-	-
2.1434	52500	0.0316	-	-
2.1475	52600	0.0523	-	-
2.1515	52700	0.0728	-	-
2.1556	52800	0.0262	-	-
2.1597	52900	0.0272	-	-
2.1638	53000	0.0092	-	-
2.1679	53100	0.04	-	-
2.1720	53200	0.0636	-	-
2.1760	53300	0.1029	-	-
2.1801	53400	0.0581	-	-
2.1842	53500	0.0899	-	-
2.1883	53600	0.0579	-	-
2.1924	53700	0.0356	-	-
2.1965	53800	0.0294	-	-
2.2005	53900	0.0479	-	-
2.2046	54000	0.0549	-	-
2.2087	54100	0.0505	-	-
2.2128	54200	0.044	-	-
2.2169	54300	0.034	-	-
2.2210	54400	0.0858	-	-
2.2250	54500	0.0266	-	-
2.2291	54600	0.0744	-	-
2.2332	54700	0.0552	-	-
2.2373	54800	0.0351	-	-
2.2414	54900	0.0357	-	-
2.2454	55000	0.036	-	-
2.2495	55100	0.036	-	-
2.2536	55200	0.0444	-	-
2.2577	55300	0.0339	-	-
2.2618	55400	0.0557	-	-
2.2659	55500	0.0575	-	-
2.2699	55600	0.0783	-	-
2.2740	55700	0.1049	-	-
2.2781	55800	0.0583	-	-
2.2822	55900	0.0394	-	-
2.2863	56000	0.0542	-	-
2.2904	56100	0.0194	-	-
2.2944	56200	0.093	-	-
2.2985	56300	0.0522	-	-
2.3026	56400	0.0737	-	-
2.3067	56500	0.0594	-	-
2.3108	56600	0.0766	-	-
2.3149	56700	0.0847	-	-
2.3189	56800	0.0766	-	-
2.3230	56900	0.0813	-	-
2.3271	57000	0.0527	-	-
2.3312	57100	0.0565	-	-
2.3353	57200	0.0371	-	-
2.3393	57300	0.0311	-	-
2.3434	57400	0.0319	-	-
2.3475	57500	0.0847	-	-
2.3516	57600	0.0587	-	-
2.3557	57700	0.0111	-	-
2.3598	57800	0.0204	-	-
2.3638	57900	0.0388	-	-
2.3679	58000	0.0566	-	-
2.3720	58100	0.055	-	-
2.3761	58200	0.0254	-	-
2.3802	58300	0.0195	-	-
2.3843	58400	0.0489	-	-
2.3883	58500	0.0668	-	-
2.3924	58600	0.0672	-	-
2.3965	58700	0.0632	-	-
2.4006	58800	0.0664	-	-
2.4047	58900	0.0278	-	-
2.4088	59000	0.0429	-	-
2.4128	59100	0.0297	-	-
2.4169	59200	0.0285	-	-
2.4210	59300	0.0384	-	-
2.4251	59400	0.0343	-	-
2.4292	59500	0.0362	-	-
2.4332	59600	0.0263	-	-
2.4373	59700	0.035	-	-
2.4414	59800	0.0405	-	-
2.4455	59900	0.0342	-	-
2.4496	60000	0.0357	0.0604	0.2430
2.4537	60100	0.0431	-	-
2.4577	60200	0.02	-	-
2.4618	60300	0.0791	-	-
2.4659	60400	0.0285	-	-
2.4700	60500	0.055	-	-
2.4741	60600	0.0699	-	-
2.4782	60700	0.0357	-	-
2.4822	60800	0.0413	-	-
2.4863	60900	0.0772	-	-
2.4904	61000	0.0516	-	-
2.4945	61100	0.0735	-	-
2.4986	61200	0.062	-	-
2.5027	61300	0.0387	-	-
2.5067	61400	0.054	-	-
2.5108	61500	0.0713	-	-
2.5149	61600	0.0476	-	-
2.5190	61700	0.0232	-	-
2.5231	61800	0.0357	-	-
2.5271	61900	0.0145	-	-
2.5312	62000	0.0249	-	-
2.5353	62100	0.0805	-	-
2.5394	62200	0.0265	-	-
2.5435	62300	0.0338	-	-
2.5476	62400	0.0645	-	-
2.5516	62500	0.0528	-	-
2.5557	62600	0.0812	-	-
2.5598	62700	0.0631	-	-
2.5639	62800	0.0179	-	-
2.5680	62900	0.0594	-	-
2.5721	63000	0.0603	-	-
2.5761	63100	0.0387	-	-
2.5802	63200	0.0476	-	-
2.5843	63300	0.0507	-	-
2.5884	63400	0.1135	-	-
2.5925	63500	0.0276	-	-
2.5966	63600	0.0509	-	-
2.6006	63700	0.0112	-	-
2.6047	63800	0.0288	-	-
2.6088	63900	0.036	-	-
2.6129	64000	0.0188	-	-
2.6170	64100	0.0489	-	-
2.6211	64200	0.0361	-	-
2.6251	64300	0.0592	-	-
2.6292	64400	0.0238	-	-
2.6333	64500	0.0167	-	-
2.6374	64600	0.0304	-	-
2.6415	64700	0.0458	-	-
2.6455	64800	0.0211	-	-
2.6496	64900	0.0522	-	-
2.6537	65000	0.0431	-	-
2.6578	65100	0.0343	-	-
2.6619	65200	0.052	-	-
2.6660	65300	0.043	-	-
2.6700	65400	0.0885	-	-
2.6741	65500	0.0242	-	-
2.6782	65600	0.0277	-	-
2.6823	65700	0.0439	-	-
2.6864	65800	0.0562	-	-
2.6905	65900	0.0411	-	-
2.6945	66000	0.0337	-	-
2.6986	66100	0.0146	-	-
2.7027	66200	0.0536	-	-
2.7068	66300	0.0626	-	-
2.7109	66400	0.0395	-	-
2.7150	66500	0.0454	-	-
2.7190	66600	0.0242	-	-
2.7231	66700	0.0165	-	-
2.7272	66800	0.0266	-	-
2.7313	66900	0.0492	-	-
2.7354	67000	0.0321	-	-
2.7394	67100	0.0661	-	-
2.7435	67200	0.0819	-	-
2.7476	67300	0.021	-	-
2.7517	67400	0.0299	-	-
2.7558	67500	0.0737	-	-
2.7599	67600	0.0577	-	-
2.7639	67700	0.0338	-	-
2.7680	67800	0.0726	-	-
2.7721	67900	0.0271	-	-
2.7762	68000	0.0328	-	-
2.7803	68100	0.023	-	-
2.7844	68200	0.0422	-	-
2.7884	68300	0.0552	-	-
2.7925	68400	0.0378	-	-
2.7966	68500	0.0128	-	-
2.8007	68600	0.0417	-	-
2.8048	68700	0.0572	-	-
2.8089	68800	0.0261	-	-
2.8129	68900	0.0379	-	-
2.8170	69000	0.034	-	-
2.8211	69100	0.037	-	-
2.8252	69200	0.0173	-	-
2.8293	69300	0.022	-	-
2.8333	69400	0.0151	-	-
2.8374	69500	0.0375	-	-
2.8415	69600	0.0468	-	-
2.8456	69700	0.0422	-	-
2.8497	69800	0.048	-	-
2.8538	69900	0.0262	-	-
2.8578	70000	0.0482	0.0576	0.2521
2.8619	70100	0.0344	-	-
2.8660	70200	0.0172	-	-
2.8701	70300	0.041	-	-
2.8742	70400	0.037	-	-
2.8783	70500	0.0088	-	-
2.8823	70600	0.0034	-	-
2.8864	70700	0.0193	-	-
2.8905	70800	0.0377	-	-
2.8946	70900	0.0553	-	-
2.8987	71000	0.0167	-	-
2.9028	71100	0.0481	-	-
2.9068	71200	0.0643	-	-
2.9109	71300	0.0222	-	-
2.9150	71400	0.0259	-	-
2.9191	71500	0.0784	-	-
2.9232	71600	0.0412	-	-
2.9272	71700	0.0568	-	-
2.9313	71800	0.0689	-	-
2.9354	71900	0.046	-	-
2.9395	72000	0.044	-	-
2.9436	72100	0.0324	-	-
2.9477	72200	0.0354	-	-
2.9517	72300	0.0486	-	-
2.9558	72400	0.0173	-	-
2.9599	72500	0.0844	-	-
2.9640	72600	0.0332	-	-
2.9681	72700	0.0723	-	-
2.9722	72800	0.0589	-	-
2.9762	72900	0.0413	-	-
2.9803	73000	0.0194	-	-
2.9844	73100	0.0432	-	-
2.9885	73200	0.0119	-	-
2.9926	73300	0.0161	-	-
2.9967	73400	0.0317	-	-

Framework Versions

Python: 3.11.13
Sentence Transformers: 5.1.2
Transformers: 4.53.3
PyTorch: 2.6.0+cu124
Accelerate: 1.9.0
Datasets: 4.4.1
Tokenizers: 0.21.2

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}